Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full burden for behavioral disclosure. It does a commendable job: it discloses the validation, the two-step payment mechanism (invoice return plus optional direct wallet-push), the best-effort and fire-and-forget nature of NWC payment, and the explicit note that escrow release is driven by invoice payment detection, not the wallet-push. It also warns about checking the response fields and paying manually if needed. The only minor gap is that it doesn't describe the exact response structure beyond the two fields mentioned, but given no annotations, this is strong coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long (about 150 words) but every sentence earns its place. It front-loads the core action and the key validation steps, then details payment handling, then clarifies escrow release. The structure is logical: purpose → validation → payment mechanics → important caveat. It's not overly verbose; the length is justified by the complexity of the purchase flow with optional wallet integration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, nested input object, optional payment integration, and no output schema), the description is remarkably complete. It covers validation (schema and spend cap), required parameters beyond the minimal shape, payment process (invoice and optional wallet push), response fields to check, and escrow release behavior. An agent has all necessary information to invoke the tool correctly and interpret outcomes, even without an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75% (3 out of 4 properties have descriptions, with agent_wallet_connection having a clear description). The description adds significant context beyond the schema: it explains why api_key and input are required (for spend-cap enforcement and skill execution) and clarifies the purpose of agent_wallet_connection (to request payment). The description also clarifies the semantics of 'input' (must match the skill's input schema). This adds meaning beyond the raw JSON schema, especially for api_key (why it's needed) and input (why it's often required).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Purchase a skill.' It goes beyond a simple verb+resource by detailing the full flow: validation against listing schema and spend cap/allowlist, generation of a Lightning invoice, escrow holding, and payment handling. This distinguishes it from siblings like check_order_status (which checks status) and submit_skill (which likely submits/creates), making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage context and excludes alternatives implicitly. It explains when to use this tool (to purchase a skill after selecting one) and exactly what to check afterward (wallet_payment_requested/wallet_payment_error and manual payment if needed). It also clarifies the behavior regarding escrow release versus wallet-push success, which is a critical 'when' constraint. While it doesn't explicitly name sibling tools, the contrast is clear from the described flow—no other sibling is referenced, but the unique responsibilities of this tool vs. others are implicitly clarified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.